EasyOCR MCP tool
About
A Model Context Protocol (MCP) server that provides OCR capabilities using the EasyOCR library.
Explore
- 3 OCR Tools: Process images from base64, files, or URLs
- Multi-language Support: Support for 80+ languages with dynamic selection
- Flexible Output: Choose between text-only or detailed results with coordinates and confidence
- Performance Optimized: Reader caching for better performance
- Native EasyOCR Output: Returns EasyOCR's original format
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
EasyOCR MCP toolCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
uv sync
If you are running this as a server for a parent MCP application, you can configure it in your main MCP config.json.
Windows Example:
{
"mcpServers": {
"easyocr-mcp": {
"command": "uv",
"args": [
"--directory",
"X:\\path\\to\\your\\project\\easyocr-mcp",
"run",
"easyocr-mcp.py"
],
"env": {
"EASYOCR_LANGUAGES": "en,ch_tra,ja"
}
}
}
}
Linux/macOS Example:
{
"mcpServers": {
"easyocr-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/your/project/easyocr-mcp",
"run",
"easyocr-mcp.py"
],
"env": {
"EASYOCR_LANGUAGES": "en,ch_tra,ja"
}
}
}
}
- EASYOCR_LANGUAGES: Comma-separated list of language codes (default: en)
- Examples: en, en,ch_sim, ja,ko,en
GPU usage is determined at installation time based on your PyTorch installation. No runtime configuration needed.
1. ocr_image_base64 - Process base64 encoded images
2. ocr_image_file - Process image files from disk
3. ocr_image_url - Process images from URLs
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"easyocr mcp tool": {
"easyocr-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/your/project/easyocr-mcp",
"run",
"easyocr-mcp.py"
],
"env": {
"EASYOCR_LANGUAGES": "en,ch_tra,ja"
}
}
}
}
}McpServers
{
"easyocr-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/your/project/easyocr-mcp",
"run",
"easyocr-mcp.py"
],
"env": {
"EASYOCR_LANGUAGES": "en,ch_tra,ja"
}
}
}EasyOCR MCP Server
A Model Context Protocol (MCP) server that provides OCR capabilities using the EasyOCR library.
> About EasyOCR:
> EasyOCR is an open-source Optical Character Recognition (OCR) library developed by JaidedAI. It supports over 80 languages, offers GPU acceleration, and is known for its ease of use and high accuracy. EasyOCR can extract text from images, scanned documents, and photos, making it suitable for a wide range of OCR tasks. For more details, visit the EasyOCR GitHub repository.
Features
- 3 OCR Tools: Process images from base64, files, or URLs
- Multi-language Support: Support for 80+ languages with dynamic selection
- Flexible Output: Choose between text-only or detailed results with coordinates and confidence
- Performance Optimized: Reader caching for better performance
- Native EasyOCR Output: Returns EasyOCR's original format
Installation
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
